© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 32982
    Prev
    Next
    INDEX
    Explanations

    Monolog, ôse Decrees, ML Chart, resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     terr
    -0.11
     lint
    -0.10
     Ley
    -0.09
     eup
    -0.09
    illy
    -0.09
    rss
    -0.08
    iffe
    -0.08
     undone
    -0.08
    elden
    -0.08
     gir
    -0.08
    POSITIVE LOGITS
     jab
    0.10
    pai
    0.10
     alike
    0.09
     Pend
    0.09
     Kale
    0.09
     temporary
    0.09
    ERE
    0.09
     Meadow
    0.09
    .watch
    0.08
     Cinder
    0.08
    Activations Density 0.001%

    No Known Activations